Triple
T27956103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yongding Hakka |
E703552
|
entity |
| Predicate | isSourceOfLoanwordsFor |
P141048
|
FINISHED |
| Object | Taiwanese Hakka lexicon |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Taiwanese Hakka lexicon | Statement: [Yongding Hakka, isSourceOfLoanwordsFor, Taiwanese Hakka lexicon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSourceOfLoanwordsFor Context triple: [Yongding Hakka, isSourceOfLoanwordsFor, Taiwanese Hakka lexicon]
-
A.
hasSourceLanguageForLoanwords
chosen
Indicates that a language serves as the original source from which loanwords are borrowed into another language.
-
B.
hasCommonLoanwordsFrom
Indicates that two languages share loanwords that originate from the same source language.
-
C.
loanwordsFrom
Indicates that one language has borrowed words from another language.
-
D.
hasLanguageFormOf
Indicates that one entity is a specific linguistic form, expression, or realization of the language used by another entity.
-
E.
sharesLinguisticFamilyWith
Indicates that two languages belong to the same linguistic family or branch within a language family.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ef840c8b2c8190946ae9522774ba51 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63b317e048190963989b732b25b91 |
completed | May 2, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f6370ea79c81909b761821ee0fa698 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 7:28 p.m.